Large Language Model Memory

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 317% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 132

All topics

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
Apr 16, 2026Seyun Bae, Seokhan Lee, Eunho YangLarge Language Model Unlearning Forgetting
1KT Corporation · 2KAIST
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Mar 3, 2026Jiejun Tan, Zhicheng Dou, Liancheng Zhang +3Large Language Model Memory Social Reasoning
Gaoling School of Artificial Intelligence · Renmin University of China · Beijing, China
Understanding LoRA as Knowledge Memory: An Empirical Analysis
Mar 1, 2026Seungju Back, Dongwoo Lee, Naun Kang +4Large Language Model Memory Long-Context Reasoning
1KAIST · 2Samsung SDS · 3New York University
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
Feb 21, 2026Chahana Dahal, Ashutosh Balasubramaniam, Zuobin XiongLarge Language Model Unlearning Knowledge Graphs
University of Nevada, Las Vegas · Indian Institute of Technology Guwahati
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Jan 30, 2026Zhixiang Zhang, Zesen Liu, Yuchong Xie +2Attacker Large Language Model Large Language Model Memory
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · Fudan University
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Jan 12, 2026Xin Cheng, Rui Tian, Wangding Zeng +18Large Language Model Memory Mixture-Of-Experts
Peking University · DeepSeek-AI
Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
Nov 25, 2025Xuyuan Liu, Shengyu Chen, Xinshuai Dong +6Multimodal Knowledge Editing Large Language Model Memory
Dartmouth College · NEC Laboratories America · Carnegie Mellon University
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Nov 25, 2025Zhen Zeng, Leijiang Gu, Zhangling Duan +4Large Language Model Unlearning Multimodal Large Language Models
Hefei University of Technology, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China · University of Amsterdam, the Netherlands
BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models
Nov 7, 2025Chandra Vamsi Krishna Alla, Harish Naidu Gaddam, Manohar Kommi +1Large Language Model Memory Efficient Long-Context Inference
University of Texas at Arlington
Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
Oct 26, 2025Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini +2In-Context Learning Large Language Model Memory
Department of Computer Science Indiana University Bloomington
Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement Policies
Nov 12, 2024Kyoungmin Kim, Jiacheng Li, Kijae Hong +3LLM Inference Optimization Graphics Processing Unit Resources
EPFL, Switzerland · NUS, Singapore · POSTECH, South Korea
SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
Date pendingMaryam Haghifam, Jason Cong, Yizhou SunEfficient Long-Context Inference Long-Context Reasoning
University of California, Los Angeles, USA

Apr 16, 2026, cs.CLJ/K move · Enter open · S save

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge

Seyun Bae, Seokhan Lee, Eunho Yang

1KT Corporation · 2KAIST

Large Language Model Unlearning Forgetting Large Language Model Memory Preservation Real-Time Systems

Open paper AskPDF arXiv

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques overlook the need for continuous and immediate action, causing them to suffer from degraded utility as updates accumulate and protracted exposure of sensitive information. To address these issues, we propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE). Our method begins by training a sentence embedding model on a dataset designed to enable the formation of sharp decision boundaries for determining whether a given input prompt corresponds to any stored forget requests. The similarity of a given input to the forget requests is then used to determine whether to answer or return a refusal response. We show that even with such a simple approach, not only does CURaTE achieve more effective forgetting than existing methods, but by avoiding modification of the language model parameters, it also maintains near perfect knowledge preservation over any number of updates and is the only method capable of continual unlearning in real-time.

Momentum

Related topics

Latest papers 132